© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118429
    Prev
    Next
    INDEX
    Explanations

    United States Bankruptcy Court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    早在
    -0.06
     ইতো
    -0.06
     additional
    -0.06
     noviembre
    -0.06
    主要是
    -0.06
     Sousa
    -0.05
     दुसरी
    -0.05
    还有一个
    -0.05
     forno
    -0.05
     aggiungere
    -0.05
    POSITIVE LOGITS
     you
    0.07
    based
    0.06
     things
    0.06
    Domestic
    0.06
     using
    0.06
     each
    0.06
    ണ്ടാ
    0.06
     they
    0.06
    !)
    0.06
    ίναι
    0.06
    Activations Density 0.001%

    No Known Activations